65 citations · 142 across the 12 of their papers we have counts for
12 papers
Privacy Auditing of Large Language Models
Ashwinee Panda, Xinyu Tang, Milad Nasr +2
Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership i…
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Ashwinee Panda, Berivan Isik, Xiangyu Qi +3
Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive int…
Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu +5
The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many…
Teach LLMs to Phish: Stealing Private Information from Language Models
Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang +2
When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a…
Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Xinyu Tang, Ashwinee Panda, Milad Nasr +2
Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation m…
Visual Adversarial Examples Jailbreak Aligned Large Language Models
Xiangyu Qi, Kaixuan Huang, Ashwinee Panda +3
Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This…
Differentially Private Image Classification by Learning Priors from Random Processes
Xinyu Tang, Ashwinee Panda, Vikash Sehwag +1
In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition.…
Privacy-Preserving In-Context Learning for Large Language Models
Tong Wu, Ashwinee Panda, Jiachen T. Wang +1
In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby im…
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar +2
An open problem in differentially private deep learning is hyperparameter optimization (HPO). DP-SGD introduces new hyperparameters and complicates existing ones, forcing researche…
Neurotoxin: Durable Backdoors in Federated Learning
Zhengming Zhang, Ashwinee Panda, Linyue Song +5
Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the…
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji +2
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning…
FetchSGD: Communication-Efficient Federated Learning with Sketching
Daniel Rothchild, Ashwinee Panda, Enayat Ullah +5
Existing approaches to federated learning suffer from a communication bottleneck as well as convergence issues due to sparse client participation. In this paper we introduce a nove…